Last Update: January, 2018
1. Course Objective
Learn Deep Learning Regression main topics using R statistical software® in this practical course for all knowledge levels. Feel free to take a look at Course Curriculum.
2. Skills Learned
At the end of this course you will know how to:
- Create target and predictor algorithm features (supervised regression deep learning task).
- Select relevant predictor features subset through univariate filter methods (Student’s t-test, ANOVA F-test) and extract predictor features transformations (principal component analysis PCA, stacked autoencoders, restricted Boltzmann machines RBM and deep belief networks DBN).
- Train algorithms such as artificial neural networks ANN, deep neural networks DNN and recurrent neural networks RNN.
- Regularize algorithm learning (nodes connections weight decay, visible or hidden layers dropout fractions, stochastic gradient descent algorithm SGD learning rate).
- Reduce recurrent neural network RNN vanishing gradient problem (long short-term memory LSTM units).
- Test algorithms forecasting accuracy (mean absolute error, root mean squared error, mean absolute percentage error).
3. Typical Student
This course is ideal for you as:
- Undergraduate or postgraduate who wants to learn about the subject.
- Academic researcher who wishes to deepen your knowledge in data mining, applied statistical learning or artificial intelligence.
- Business data scientist who desires to apply this knowledge in areas such as consumer analytics, finance, banking, health care, e-commerce or social media.